Journal of Scientific Research and Reports

Artificial intelligence (AI) and machine learning (ML) are increasingly investigated as decision-support technologies for supply chain management (SCM), yet their value depends on the nature of the decision, data availability, organisational capability and the methods used to evaluate outcomes. This critical narrative review examines applications across demand forecasting, inventory planning, sourcing, manufacturing, logistics, risk management and sustainability. It brings together relevant peer-reviewed reviews, conceptual contributions and empirical studies, and distinguishes evidence from operational deployments from results reported in literature syntheses or simulations. The literature supports the practical relevance of data-driven prediction, pattern detection and decision augmentation, but it does not establish uniform improvements in cost, forecast accuracy, resilience or environmental performance across settings. Reviewed research also identifies integration costs, fragmented data, process misalignment, model drift, limited transparency and governance concerns as barriers to realising benefits. Recent work on generative AI broadens possible applications to document-intensive processes, synthetic scenarios and interactive decision support, while indicating that field-based validation remains limited. A process-oriented framework is proposed in which analytics inform planning, procurement, manufacturing, distribution and inventory decisions under continuous human oversight. The review argues that useful evaluations should compare AI-supported decisions against relevant operational baselines, account for service levels and cost trade-offs, and document transferability across sectors and resource settings. Future research should prioritise longitudinal field studies, cross-organisational coordination, responsible deployment and context-sensitive applications in emerging economies.